python 爬爬爬 基本函数～

 

https://docs.python.org/2/howto/urllib2.html#data

http://zhuoqiang.me/python-urllib2-usage.html

 

#!/usr/bin/env python
# -*- coding: utf-8 -*-

import os
import urllib
import urllib2
import re
import cookielib

httpHandler = urllib2.HTTPHandler(debuglevel=1)
httpsHandler = urllib2.HTTPSHandler(debuglevel=1)
opener = urllib2.build_opener(httpHandler, httpsHandler)
urllib2.install_opener(opener)


headers = {'User-Agent' : 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2272.118 Safari/537.36'}
values = {
    #'username':'xxx',
    #'password':'xxx',
}
postdata = urllib.urlencode(values)            # 表单

# GET
req = urllib2.Request(url='https://www.baidu.com/', data=None, headers=headers)
response = urllib2.urlopen(req)
html = response.read()
response.close()
print html

# 图片等二进制数据
req = urllib2.Request(url='https://www.baidu.com/img/bd_logo1.png', data=postdata, headers=headers)
operate = opener.open(req)
data = operate.read()
operate.close()

f = open('baidu.png', 'wb')
f.write(data)
f.flush()
f.close()